Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    scandals and crises

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    naires
    -0.08
    divide
    -0.07
     lets
    -0.07
    rawtypes
    -0.06
     vids
    -0.06
     %.
    -0.06
     boxShadow
    -0.06
     подв
    -0.06
     burst
    -0.06
     "%.
    -0.06
    POSITIVE LOGITS
    ROSS
    0.07
    ilip
    0.06
     heals
    0.06
    AP
    0.06
    	output
    0.06
     ชนะ
    0.06
     instituted
    0.06
     AK
    0.06
    ันได
    0.06
    己
    0.06
    Act Density 0.065%

    No Known Activations